Thorsten Peinemann

Hi, hello.

About me

I am a fourth-year PhD candidate with the Institute for IT Security at University of Luebeck, advised by Esfandiar Mohammadi. My main interests are differential privacy and machine learning. I want to improve the utility-privacy trade-offs of algorithms.

Outside of work, I enjoy spending time with my wife, working out and spending time outdoors with my dog.

Recent news

  • March 2025: Represented my research group at the National Conference of IT Security Research of the BMBF.
  • October 2024: Gave a talk at CCS 2024 with Moritz Kirschte.
  • September 2024: Presented a poster at TPDP 2024 with Moritz Kirschte.
  • September 2024: Gave a teaser talk at KI Med Connect 2024.
  • April 2024: Presented a poster at AnoSiDat 2024 with Moritz Kirschte.

Publications and Preprints

MammothDP: Differentially Private Boosted Decision Trees, hyperparameter-free and ready for Trusted Hardware
Moritz Kirschte, Thorsten Peinemann, Kari Kostiainen, Jan Wichelmann, Thomas Eisenbarth, Esfandiar Mohammadi
In Submission. [PDF]

S-BDT: Distributed Differentially Private Gradient Boosted Decision Trees
Thorsten Peinemann*, Moritz Kirschte*, Joshua Stock, Carlos Cotrini, Esfandiar Mohammadi
*The first two authors equally contributed to this work.
CCS 2024 [PDF] [Code]